135 search results - page 6 / 27 » Temporal Feature Selection for Noisy Speech Recognition |
ISCAS
2008
IEEE
15 years 4 months ago
2008
IEEE
Abstract— Especially for tasks like automatic meeting transcription, it would be useful to automatically recognize speech also while multiple speakers are talking simultaneously....
ICASSP
2008
IEEE
15 years 4 months ago
2008
IEEE
Missing data techniques have been recently applied to speaker recognition to increase performance in noisy environments. The drawback of these techniques is the vulnerability of t...
ICML
2006
IEEE
15 years 10 months ago
2006
IEEE
Many real-world sequence learning tasks require the prediction of sequences of labels from noisy, unsegmented input data. In speech recognition, for example, an acoustic signal is...
ICASSP
2008
IEEE
15 years 4 months ago
2008
IEEE
In this paper, we propose a novel approach to feature compensation performed in the cepstral domain. We apply the linear approximation method in the cepstral domain to simplify th...
ICPR
2010
IEEE
15 years 1 months ago
2010
IEEE
Person identification using audio (speech) and visual (facial appearance, static or dynamic) modalities, either independently or jointly, is a thoroughly investigated problem in pa...